cs.LG（2025-05-21）

📊 共 9 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (6 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (2 🔗2) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (6 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Learning to Rank Chain-of-Thought: Using a Small Model	提出能量结果奖励模型以提高数学推理的准确性	large language model chain-of-thought
2	MoTime: A Dataset Suite for Multimodal Time Series Forecasting	提出MoTime数据集以解决多模态时间序列预测问题	multimodal
3	Harnessing On-Device Large Language Model: Empirical Results and Implications for AI PC	提出系统化方法评估边缘设备上的大型语言模型性能	large language model	✅
4	Human-centered Interactive Learning via MLLMs for Text-to-Image Person Re-identification	提出人本交互学习框架以提升文本到图像的行人重识别效果	large language model multimodal
5	Why and When Deep is Better than Shallow: An Implementation-Agnostic State-Transition View of Depth Supremacy	提出深度优于浅层的理论框架以解决模型泛化问题	chain-of-thought
6	PiFlow: Principle-aware Scientific Discovery with Multi-Agent Collaboration	提出PiFlow以解决科学发现中的不确定性问题	large language model	✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (2 篇)

#	题目	一句话要点	标签	🔗	⭐
7	RLBenchNet: The Right Network for the Right Reinforcement Learning Task	提出RLBenchNet以优化强化学习任务中的网络选择	reinforcement learning Mamba	✅
8	RL Tango: Reinforcing Generator and Verifier Together for Language Reasoning	提出Tango框架以解决LLM推理能力不足问题	reinforcement learning large language model	✅

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
9	Covert Attacks on Machine Learning Training in Passively Secure MPC	提出有效攻击以揭示被动安全MPC训练中的隐患	MPC

⬅️ 返回 cs.LG 首页 · 🏠 返回主页